{"total":142,"rows":[{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406,"area":"mllm"},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190,"area":null},{"id":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166,"area":null},{"id":"2203.12745","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","created":"2022-03-23","cited_by_count":148,"area":null},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"area":null},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99,"area":null},{"id":"2101.06072","title":"Video Summarization Using Deep Neural Networks: A Survey","created":"2021-01-15","cited_by_count":85,"area":null},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"area":null},{"id":"2401.02309","title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46,"area":null},{"id":"2108.11510","title":"Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey","created":"2021-08-25","cited_by_count":43,"area":null},{"id":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41,"area":null},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40,"area":null},{"id":"2108.11770","title":"Cross-category Video Highlight Detection via Set-based Learning","created":"2021-08-26","cited_by_count":38,"area":null},{"id":"2510.27280","title":"FOCUS: Efficient Keyframe Selection for Long Video Understanding","created":"2025-10-31","cited_by_count":37,"area":"mllm"},{"id":"2208.06773","title":"TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency","created":"2022-08-14","cited_by_count":35,"area":null},{"id":"2105.04066","title":"Reconstructive Sequence-Graph Network for Video Summarization","created":"2021-05-10","cited_by_count":34,"area":null},{"id":"2404.00801","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","created":"2024-03-31","cited_by_count":34,"area":null},{"id":"2311.08835","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","created":"2023-11-15","cited_by_count":31,"area":null},{"id":"2312.00083","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","created":"2023-11-30","cited_by_count":29,"area":null},{"id":"2210.16422","title":"Toward Unifying Text Segmentation and Long Document Summarization","created":"2022-10-28","cited_by_count":28,"area":null},{"id":"2204.08121","title":"End-to-end Dense Video Captioning as Sequence Generation","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2104.11530","title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","created":"2021-04-23","cited_by_count":26,"area":null},{"id":"2104.12465","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","created":"2021-04-26","cited_by_count":26,"area":null},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25,"area":null},{"id":"2404.09263","title":"Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection","created":"2024-04-14","cited_by_count":25,"area":null},{"id":"2405.11905","title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","created":"2024-05-20","cited_by_count":23,"area":null},{"id":"2407.15850","title":"AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description","created":"2024-07-22","cited_by_count":23,"area":null},{"id":"2106.10528","title":"Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net","created":"2021-06-19","cited_by_count":22,"area":null},{"id":"2201.02494","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","created":"2022-01-07","cited_by_count":21,"area":null},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21,"area":null},{"id":"2109.10559","title":"Hierarchical Multimodal Transformer to Summarize Videos","created":"2021-09-22","cited_by_count":19,"area":null},{"id":"2109.14834","title":"IntentVizor: Towards Generic Query Guided Interactive Video Summarization","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2104.02841","title":"Learning Triadic Belief Dynamics in Nonverbal Communication from Videos","created":"2021-04-07","cited_by_count":17,"area":null},{"id":"2404.03398","title":"Scaling Up Video Summarization Pretraining with Large Language Models","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2204.04615","title":"Learning Pixel-Level Distinctions for Video Highlight Detection","created":"2022-04-10","cited_by_count":16,"area":null},{"id":"2504.11199","title":"Video Summarization with Large Language Models","created":"2025-04-15","cited_by_count":16,"area":null},{"id":"2112.10194","title":"UnweaveNet: Unweaving Activity Stories","created":"2021-12-19","cited_by_count":14,"area":null},{"id":"2105.14678","title":"Image-to-Video Generation via 3D Facial Dynamics","created":"2021-05-31","cited_by_count":13,"area":null},{"id":"2307.01945","title":"Query-based Video Summarization with Pseudo Label Supervision","created":"2023-07-04","cited_by_count":13,"area":null},{"id":"2306.04216","title":"MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos","created":"2023-06-07","cited_by_count":12,"area":null},{"id":"2112.13478","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","created":"2021-12-27","cited_by_count":10,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2403.11463","title":"Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding","created":"2024-03-18","cited_by_count":10,"area":null},{"id":"2206.10157","title":"Probing Visual-Audio Representation for Video Highlight Detection via Hard-Pairs Guided Contrastive Learning","created":"2022-06-21","cited_by_count":9,"area":null},{"id":"2309.11091","title":"Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval","created":"2023-09-20","cited_by_count":9,"area":null},{"id":"2404.03477","title":"Towards Automated Movie Trailer Generation","created":"2024-04-04","cited_by_count":9,"area":null},{"id":"2105.06441","title":"DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization","created":"2021-05-13","cited_by_count":8,"area":null},{"id":"2202.10680","title":"Submodlib: A Submodular Optimization Library","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2305.00455","title":"Causalainer: Causal Explainer for Automatic Video Summarization","created":"2023-04-30","cited_by_count":8,"area":null},{"id":"2501.10787","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2201.04024","title":"Smart Director: An Event-Driven Directing System for Live Broadcasting","created":"2022-01-11","cited_by_count":7,"area":null},{"id":"2309.11569","title":"Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding","created":"2023-09-20","cited_by_count":7,"area":null},{"id":"2403.09401","title":"Unsupervised Modality-Transferable Video Highlight Detection with Representation Activation Sequence Learning","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2101.10514","title":"How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarization","created":"2021-01-26","cited_by_count":6,"area":null},{"id":"2109.01799","title":"PR-Net: Preference Reasoning for Personalized Video Highlight Detection","created":"2021-09-04","cited_by_count":6,"area":null},{"id":"2205.06253","title":"What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2210.05840","title":"LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videos","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2210.11707","title":"Video Summarization Overview","created":"2022-10-21","cited_by_count":6,"area":null},{"id":"2311.12159","title":"Conditional Modeling Based Automatic Video Summarization","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2403.01437","title":"GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features","created":"2024-03-03","cited_by_count":6,"area":null},{"id":"2404.04511","title":"Cluster-based Video Summarization with Temporal Context Awareness","created":"2024-04-06","cited_by_count":6,"area":null},{"id":"2407.13933","title":"Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence","created":"2024-07-18","cited_by_count":6,"area":null},{"id":"2410.11133","title":"3D-Prover: Diversity Driven Theorem Proving With Determinantal Point Processes","created":"2024-10-14","cited_by_count":6,"area":null},{"id":"2501.12254","title":"Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos","created":"2025-01-21","cited_by_count":6,"area":null},{"id":"2511.00141","title":"FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding","created":"2025-10-31","cited_by_count":6,"area":"lr"},{"id":"2105.07667","title":"AudioVisual Video Summarization","created":"2021-05-17","cited_by_count":5,"area":null},{"id":"2211.10056","title":"Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization","created":"2022-11-18","cited_by_count":5,"area":null},{"id":"2501.14114","title":"LeCoPCR: Legal Concept-guided Prior Case Retrieval for European Court of Human Rights cases","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2508.15389","title":"Spiking Variational Graph Representation Inference for Video Summarization","created":"2025-08-21","cited_by_count":5,"area":null},{"id":"2207.01814","title":"Multimodal Frame-Scoring Transformer for Video Summarization","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2209.15501","title":"A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2305.17569","title":"Collaborative Multi-Agent Video Fast-Forwarding","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2510.08458","title":"SummDiff: Generative Modeling of Video Summarization with Diffusion","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2101.11111","title":"Automatic Comic Generation with Stylistic Multi-page Layouts and Emotion-driven Text Balloon Generation","created":"2021-01-26","cited_by_count":3,"area":null},{"id":"2107.03783","title":"Use of Affective Visual Information for Summarization of Human-Centric Videos","created":"2021-07-08","cited_by_count":3,"area":null},{"id":"2109.02625","title":"ERA: Entity Relationship Aware Video Summarization with Wasserstein GAN","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2110.01774","title":"HighlightMe: Detecting Highlights from Human-Centric Videos","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2309.13446","title":"Video Timeline Modeling For News Story Understanding","created":"2023-09-23","cited_by_count":3,"area":null},{"id":"2311.03745","title":"Unsupervised Video Summarization via Iterative Training and Simplified GAN","created":"2023-11-07","cited_by_count":3,"area":null},{"id":"2405.08890","title":"Language-Guided Self-Supervised Video Summarization Using Text Semantic Matching Considering the Diversity of the Video","created":"2024-05-14","cited_by_count":3,"area":null},{"id":"2412.01558","title":"VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval","created":"2024-12-02","cited_by_count":3,"area":"mllm"},{"id":"2503.00364","title":"CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion","created":"2025-03-01","cited_by_count":3,"area":null},{"id":"2506.10807","title":"Prompts to Summaries: Zero-Shot Language-Guided Video Summarization with Large Language and Video Models","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2511.10953","title":"Language-Guided Graph Representation Learning for Video Summarization","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2203.15778","title":"Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method","created":"2022-03-29","cited_by_count":2,"area":null},{"id":"2204.08352","title":"MHSCNet: A Multimodal Hierarchical Shot-aware Convolutional Network for Video Summarization","created":"2022-04-18","cited_by_count":2,"area":null},{"id":"2206.04888","title":"AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2207.00782","title":"Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2207.08352","title":"Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention","created":"2022-07-18","cited_by_count":2,"area":null},{"id":"2306.01395","title":"Masked Autoencoder for Unsupervised Video Summarization","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2308.15109","title":"DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection","created":"2023-08-29","cited_by_count":2,"area":"diffusion"},{"id":"2309.09405","title":"Does Video Summarization Require Videos? Quantifying the Effectiveness of Language in Video Summarization","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2407.12002","title":"A Multimodal Transformer for Live Streaming Highlight Prediction","created":"2024-06-15","cited_by_count":2,"area":null},{"id":"2501.06138","title":"MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos","created":"2025-01-10","cited_by_count":2,"area":"ssm"},{"id":"2505.06557","title":"Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining","created":"2025-05-10","cited_by_count":2,"area":null},{"id":"2506.20588","title":"TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness","created":"2025-06-25","cited_by_count":2,"area":null}],"next_cursor":"100"}